CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing

@article{Jin2021CaseNetCS,
  title={CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing},
  author={X. Jin and Cuiling Lan and Wenjun Zeng and Zhizheng Zhang and Zhibo Chen},
  journal={Neurocomputing},
  year={2021},
  volume={419},
  pages={9-22}
}
Objects in an image exhibit diverse scales. Adaptive receptive fields are expected to catch suitable range of context for accurate pixel level semantic prediction for handling objects of diverse sizes. Recently, atrous convolution with different dilation rates has been used to generate features of multi-scales through several branches and these features are fused for prediction. However, there is a lack of explicit interaction among the branches to adaptively make full use of the contexts. In… Expand
3 Citations

References

SHOWING 1-10 OF 92 REFERENCES
Scale-Adaptive Convolutions for Scene Parsing
  • 131
  • PDF
Recurrent Scene Parsing with Perspective Understanding in the Loop
  • 65
  • PDF
Attention to Scale: Scale-Aware Semantic Image Segmentation
  • 769
  • Highly Influential
  • PDF
Dual Attention Network for Scene Segmentation
  • 943
  • Highly Influential
  • PDF
Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
  • 166
  • PDF
Dynamic attention network for semantic segmentation
  • 9
ACFNet: Attentional Class Feature Network for Semantic Segmentation
  • Fan Zhang, Yanqin Chen, +5 authors Errui Ding
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
  • 48
  • PDF
DenseASPP for Semantic Segmentation in Street Scenes
  • 401
  • Highly Influential
  • PDF
OCNet: Object Context Network for Scene Parsing
  • 221
  • PDF
Adaptive Pyramid Context Network for Semantic Segmentation
  • 64
  • PDF
...
1
2
3
4
5
...